Skills
98,284 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use when the user asks to “audit on-page SEO” or “diagnose why a single page dropped”; scores titles, meta, header structure, keyword placement, links, and images with prioritized fixes. Not for E-E-A-T / publish-readiness scoring—use content-quality-auditor; not for crawl / CWV / indexing—use technical-seo-checker. 页面SEO审计/排名诊断
Salesforce Connected Apps and OAuth configuration with 120-point scoring. TRIGGER when: user configures OAuth flows, JWT bearer auth, Connected Apps, or touches .connectedApp-meta.xml / .eca-meta.xml files. DO NOT TRIGGER when: Named Credentials for callouts (use sf-integration), permission policies (use sf-permissions), or API endpoint code (use sf-apex)
Plans, configures, and hardens Google Kubernetes Engine (GKE) security. Covers Workload Identity Federation, Secret Manager integration, RBAC hardening, Binary Authorization, Network Policies (Dataplane V2), Pod Security Standards, and IAM roles. Use when securing GKE clusters, setting up Workload Identity, hardening RBAC configurations, or configuring GKE secrets. Don't use for general network routing configuration (use gke-networking instead).
Build or refactor reusable, data-driven enemy archetype and moveset systems for Three.js action games. Use for enemy content schemas, model and rig conventions, combat move timing and contact contracts, runtime state boundaries, placeholder fallbacks, deterministic fixtures, or production playthrough validation.
Turn a brief music description and optional tagged lyrics into a professional MiniMax Music 3 structured caption with Global Metadata, Vocal Details, and a section-aware Arrangement. Use when users ask to enhance a music-generation prompt, preserve lyric-section directives, retrieve a similar style from bundled templates, fuse styles, or produce JSON or JSONL caption output.
Product review analysis and customer feedback intelligence. Pain point identification, praise pattern analysis, feature request extraction, sentiment analysis, and product improvement insights. Use when the user asks about review analysis, customer feedback, product reviews, or sentiment analysis.
Yunqi Conference discovery and planning Skill. Query the agenda and exhibition information; recommend and compare sessions and exhibitors/booths based on Agent goals; answer introductory questions about the conference theme, highlights, and venues using the conference guide; and answer attendee service questions about transportation, accommodation, dining, and tickets using the attendee guide. Use for scenarios such as “check the conference agenda,” “find exhibition information,” “recommend sessions,” “compare exhibitors/booths,” “plan an attendance route,” “conference highlights,” “conference introduction,” “transportation/accommodation/dining,” and “tickets/check-in.” The data source is the yunqi subcommand of qianwen CLI (API retrieval preferred, with the static conference guide and attendee guide as supplements). Public, read-only, and performs no write operations.
Comprehensive Amazon advertising strategy and campaign optimization. Sponsored Products, Sponsored Brands, Sponsored Display campaign management, budget allocation, ACoS optimization, and performance tracking. Use when the user asks about Amazon PPC, advertising strategy, campaign optimization, or Amazon ads management.
Generate personalized music playlists by analyzing the user's music taste and generation feedback history. Triggers on any request involving playlist generation, music taste profiling, or personalized music recommendations. Supports multilingual triggers — match equivalent phrases in any language
Build responsive, mobile-first web applications. Use when implementing responsive layouts, touch interactions, mobile navigation, or optimizing for various screen sizes. Triggers on responsive design, mobile-first, breakpoints, touch events, viewport
Create and edit professional motion graphics videos with Remotion (React-based video). Use this skill EVERY time the user wants to create a video, edit a video, animate something, build an intro/outro/logo animation, make a Reel/Short/promo/launch video, add text animations or captions to footage, composite images and B-roll into a video, or mentions Remotion, motion graphics, video rendering, or "make this video look better/less generic". Also trigger when editing an existing Remotion project or when the user complains their video looks basic, generic, or amateur — this skill contains the exact fixes. Always read this skill BEFORE writing any Remotion code.
Write, rewrite, review, or continuously refine X/Twitter posts in Meng To's current voice using his deduplicated authored-post corpus, personal and product context, shared resources, and Content repo evidence. Use when asked to improve a tweet in Meng's tone, draft an original post, reply, thread, resource share, or quote post as Meng, check whether an angle repeats an earlier post, study Meng's writing style, ingest another 20-50 authored posts, or hone the reusable Meng X voice profile.
Use for .NET / C# binary reverse engineering. Use when the target is a .NET assembly (PE header contains CLR, .exe/.dll managed program), C# compiled artifact (including NativeAOT), red-team Sharp* tools (Rubeus / SharpHound / SharpHound, etc.), .NET obfuscated program (ConfuserEx / SmartAssembly / Babel / Eazfuscator), or .NET loader / info-stealer / packed malware. Prefer dnSpyEx + de4dot; integrate dnSpy MCP when AI needs to operate directly. Not for pure native binaries (use reverse-engineering / ida-reverse).
Find images you can confidently use for free — for websites, documents, presentations, UIs, blog posts, marketing assets, or anything else — without ever worrying about licensing. This skill pulls from a curated repository of pre-vetted images, pinned to a specific human-reviewed revision, and confirms each image's license — read from the image's own embedded metadata — before handing it over, so the licensing question is already answered by the time you get the URL. Triggers on any request involving an image, photo, illustration, banner, hero, or visual asset, including phrases like 'find me an image of...', 'I need a photo of...', 'get a picture for...'. Also use this when building UIs, articles, or content where a stress-free, freely-licensed image is needed.
Turn a completed daily UI inspiration capture into exactly five original landing-page builds, one per separate Codex task, using Sites. Use when the user asks to turn the daily inspiration references, a five-item UI prompt pack, or a dated `*-ui-inspiration-capture` article into distinct HTML landing pages while changing the source brands, names, copy, people, numbers, pricing, claims, and imagery.
Build, integrate, audit, or refactor rigged monsters for Three.js and web action games. Use for monster asset contracts, procedural or imported creature rigs, semantic joints and sockets, hurtboxes and attack volumes, combat animation states, enemy-runtime adapters, LODs, deterministic review fixtures, and validating that every monster follows one shared system.
Motion / animation context for the `use_figma` MCP tool — animating Figma nodes via manual keyframes, animation styles, easing, and timeline duration. Load alongside figma-use whenever a task involves adding, editing, or inspecting animation on a node. Also covers working with custom animation styles.
A full-featured intelligent stock monitoring and alert system. Supports seven alert rules, including cost percentage, moving-average golden and death crosses, RSI overbought and oversold levels, unusual trading volume, price gaps, and dynamic take-profit. Designed for Chinese investors (red for rises, green for falls).
WORKFLOW SKILL — Manage the Aspire lifecycle in VS Code or the CLI. WHEN: "start or stop my Aspire app", "aspire_apphost_start", "aspire_apphost_stop", "notEditorOwned", "ambiguousSession", "aspire start", "aspire stop", "aspire wait", resource restart, file-lock errors (MSB3491 or CS2012), port conflicts, git worktrees, "--isolated", "aspire update --self", "aspire update --migrate", "aspire describe --include-hidden", "aspire stop --force", "aspire stop --force --volumes", integration discovery, default watch, or hot reload. INVOKES: VS Code lifecycle tools first when exposed; Aspire CLI for readiness, inspection, resource operations, isolated worktree starts, and allowed fallbacks. DO NOT USE FOR: deploy/publish/destroy (aspire-deployment), logs/traces/metrics (aspire-monitoring), terminal authoring/attach/tapes (aspire-terminals), or AppHost code and resource wiring (aspireify). FOR SINGLE OPERATIONS: Load the matching editor tool first; follow exact-target, worktree-isolation, and stop-result rules.
Create and edit 3D models in Blockbench using MCP tools. Use when building geometry with cubes, creating meshes, placing spheres/cylinders, editing vertices, extruding faces, or organizing models with groups. Covers both cube-based Minecraft modeling and freeform mesh editing.
Use when reverse-engineering frontend JavaScript with js-reverse-mcp, including signature-flow tracing, page observation and evidence collection, runtime sampling, local environment setup for reproduction, and evidence-based output. Prioritize js-reverse_* tools available in the current environment; integrate with jshookmcp when stronger browser/CDP/Hook capabilities are needed
Agent Script DSL for deterministic Agentforce agents. Trigger when users write or edit .agent files, build FSM-based agents, use the Agent Script CLI (sf agent generate authoring-bundle, sf agent validate authoring-bundle, sf agent preview, sf agent publish authoring-bundle, sf agent activate), or ask about deterministic agent patterns, slot filling, or instruction resolution. Do not trigger for Builder metadata work (use sf-ai-agentforce), agent testing (use sf-ai-agentforce-testing), or persona design (use sf-ai-agentforce-persona).
Compare and update the `computedHash` in the root `skills-lock.json` against the latest state of the upstream repository. Skip cloning entries whose `source` does not exactly match `Fandhe-AI/<repo>` (safeguard). Do not touch `skills-lock.json` files inside submodules. Use after merging contribute-skill or syncing upstream, or when asked to "update hashes" or "sync skills-lock".
Generate, refine, validate, and render diagrams from natural language, notes, code snippets, schemas, tables, or existing diagram source. Use for flowcharts, swimlanes, sequence diagrams, state diagrams, ER diagrams, class diagrams, architecture/C4-style diagrams, dependency graphs, Gantt charts, mind maps, user journeys, Sankey-style flows, org charts, network graphs, and other visual models. Supports Mermaid by default, Graphviz dot for complex graph layout, PlantUML for UML-heavy engineering diagrams, and SVG output when direct markup is more reliable.
Remove signs of AI-generated, translated, or overly mechanical Chinese prose. Use when rewriting, editing, or reviewing Chinese blog posts, essays, newsletters, nonfiction chapters, product analysis, or long-form commentary so they read like native Chinese writing. Trigger this skill when the user asks to 「去 AI 味」, 「润色成中文母语表达」, 「改得像博客或书里写的」, 「减少翻译腔」, or similar. Detect and fix translation-like phrasing, empty big words, formulaic contrast frames, sloganized endings, list inflation, punctuation misuse, terminology/casing inconsistencies, and paragraph rhythm that feels assembled rather than written
Use when writing or fixing Build.cs, Target.cs, .uproject or .uplugin files, creating a module or plugin, or resolving an Unreal build error. Also use when the user mentions 'unresolved external symbol', 'LNK2019', 'cannot open include file', 'C1083', 'MODULENAME_API', 'PublicDependencyModuleNames', 'IWYU', 'PCHUsage', 'IMPLEMENT_MODULE', 'IMPLEMENT_PRIMARY_GAME_MODULE', 'LoadingPhase', 'circular dependency', 'Missing precompiled manifest', 'EngineAssociation', 'IncludeOrderVersion', 'Live Coding'. For UCLASS/UPROPERTY rules see ue-cpp-foundations; for editor modules see ue-editor-tools; for Game Feature plugins see ue-game-features.
Provision a zero-config, no-signup, temporary Upstash Redis database for an AI agent with a single POST to https://upstash.com/start-redis, with no account, API key, or SDK setup required. Use when an agent needs scratch Redis right now and the user has not provided credentials, for short-term memory across tool calls, conversation history, a sub-agent work queue, ranked recall, or a quick prototype or demo. Covers idempotent creation and re-fetching credentials, calling the database through the body-style REST API or the official SDKs, and telling the user how to claim it. The database lives 3 days unless the user claims it; not for production data, PII, or secrets.
Expert in building 3D experiences for the web using Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and adding depth to web experiences. Use for: 3D websites, three.js, WebGL, react three fiber, and 3D experiences
The master craft of scripting short-form vertical video (Reels, TikTok, Shorts) for watch-through. Use when someone wants a short-form video script, a Reel/TikTok/Short script, help with hooks, retention, pacing, the ending/loop, sound-off captions, or fixing early drop-off. Watch-through, not likes, rules short-form; the script's only job is to be un-skippable. Uses the WATCH framework. Reads brand-profile + voice-builder first; pulls the 'what' from the content-angle skills and the hook from hook-writer. The agent writes the script (spoken lines + on-screen text + beat/shot direction + hook variants + CTA); the human shoots/performs/edits; WoopSocial publishes the finished file. Routes platform specifics to reels-script / tiktok-script / youtube-shorts; pairs with talking-head-and-piece-to-camera. NEVER bait-and-switches the hook or fabricates a stat. Distinct from hook-writer, captions-and-clipping, and ai-video/veo-3/heygen (which generate the video this scripts).
Generate and track comprehensive due diligence checklists tailored to the target company's sector, deal type, and complexity. Covers all major workstreams with request lists, status tracking, and red flag escalation. Use when kicking off diligence, organizing a data room review, or tracking outstanding items. Triggers on "dd checklist", "due diligence tracker", "diligence request list", "what do we still need", or "data room review".
Create / provision / set up a NEW Digital Experience (Communities) / Experience Cloud site — employee service, IT support, help desk, HR, customer, and partner portals — via the headless-360 MCP site-creation APIs. Use whenever a user asks to create/provision/set up a portal, site, or community, e.g.: 'create an employee service portal', 'create an IT Support Portal', 'create an Agentforce Employee Center', including wiring MIAW (Messaging for In-App/Web) at create. This is the site-CREATION skill and OWNS provisioning a new Aura OR LWR Experience Builder site from scratch — trigger it even when the user says 'Experience Builder site' or 'LWR site', as long as a NEW site is wanted. It always writes a portal-creation report as its final step (never ad hoc via CLI) and never makes a legacy Tabs+Visualforce site. DO NOT TRIGGER only for modifying an EXISTING site's pages/routes/theme/branding/guest-access metadata (experience-lwr-site-generate), existing-site customization (experience-ui-bundle), CMS, Commerce.
AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing code that uses `@spaces.GPU`, configuring `python_version` or `requirements.txt` for a ZeroGPU Space, or handling ZeroGPU-specific code constraints — pickle-based process isolation, `gr.State` semantics across the worker boundary, no `torch.compile` (use AoTI instead), CUDA wheel-only builds (no `nvcc` at build or runtime), large vs xlarge sizing, and dynamic duration callables. Make sure to use this skill whenever the user mentions ZeroGPU, `@spaces.GPU`, or the `spaces` Python package, or hits ZeroGPU-specific code errors like `PicklingError` across the worker boundary, `illegal duration`, or `flash-attn` wheel-build failures — even when the user does not explicitly ask for ZeroGPU coding guidance. Trigger on `import spaces` or `@spaces.GPU` in code.
Use when writing C++ for materials or rendering — dynamic material instances, material parameter collections, render targets, scene capture, post process, decals, Nanite, Lumen, MegaLights, Substrate. Also use when the user mentions 'MID', 'CreateDynamicMaterialInstance', 'SetScalarParameterValue', 'UMaterialInstanceDynamic', 'material parameter collection', 'UTextureRenderTarget2D', 'DrawMaterialToRenderTarget', 'scene capture', 'post process volume', 'FPostProcessSettings', 'bOverride_', 'blendable', 'decal', 'custom depth stencil', 'Nanite', 'Lumen' or 'global shader'. For Niagara materials, see ue-niagara-effects; for UMG materials, see ue-ui-umg-slate.
Build, extend, or audit production-linked browser map editors for Three.js and isometric games. Use when Codex needs to create a private director view, derive a versioned editor document from authored placements, add outliner, layer, selection, drag, snap, inspector, or camera controls, expose enemy aggro, leash, or patrol overlays, implement local draft import, export, undo, and reset, secure an editor route with IP and password sessions, or validate and release a map editor without mutating live gameplay data.
After you create or change an artifact or skill, taste-test it with our own skills instead of trusting your in-session judgment — recursive self-improvement, made automatic. Use right after writing or editing anything, before calling it done, committing, or handing it off.
Craft model-specific prompts optimized for the target checkpoint and identity method. Handles FLUX, SDXL, SD1.5, and Wan video models with proper syntax, quality tags, and negative prompts. Use when generating or refining prompts for ComfyUI workflows
Let this agent generate images, transcribe audio, and synthesize speech on the user's own machine through a local Lemonade Server instead of a paid cloud API. Use it above all to change that routing persistently, from now on — keep generating pictures locally while chat stays on the cloud; set this workspace up to make images on my own machine — even when the user asks for no image or file in the same breath. Also use it for a single request the user wants done locally, offline, on-device, or kept private: transcribe this recording, make this picture, read this text aloud. Applies in Claude, Cursor, Codex, or any agent harness. Use it when the user wants to cut cost or tokens on image, audio, or voice API calls, or drop DALL-E, hosted Whisper, ElevenLabs, or other paid multimodal APIs; or mentions Lemonade Server, OmniRouter, SD-Turbo, kokoro, Ryzen AI, or NPU/iGPU/dGPU inference. Changes no application source code; do not use it if the user is adding local AI to an app they ship.
Skill for attending the Yunqi Conference and working with its summaries. Create, batch-create, query, and cancel Agent meeting subscriptions; track subscriptions and statistics; and retrieve, follow up on, and summarize post-event summaries. Guides conversations through three stages—before, during, and after the conference: directs users to the livestream before and during, then reports preparation progress or retrieves the summary text according to its status. Use for scenarios such as “Subscribe to a meeting,” “Batch subscribe to meetings,” “View subscription list,” “Cancel subscription,” “Retrieve summary,” “Follow up on summary,” and “Summarize.” Data source: the yunqi subcommand of qianwen CLI, with subscription read/write and summary retrieval capabilities.
Create user-facing App Store release notes by collecting and summarizing all user-impacting changes since the last git tag (or a specified ref). Use when asked to generate a comprehensive release changelog, App Store "What's New" text, or release notes based on git history or tags.
Source-backed research orchestrator for the Fusion ecosystem. Routes to the correct research agent based on question type. Returns source-backed evidence only; will not invent Framework behavior, component APIs, skill catalog relationships, platform guidance, or backend implementation details. USE FOR: any research question needing source-backed evidence about Fusion Framework APIs, EDS components, the Fusion skill catalog, Fusion platform documentation, or backend service implementation. DO NOT USE FOR: implementing code changes, installing or editing skills, MCP setup or troubleshooting, or inventing Fusion behavior without evidence.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.